Investigation of High-Voltage Insulator Surface Conditions based on Machine Learning TensorFlow
DOI:
https://doi.org/10.31963/intek.v7i1.2053Keywords:
Insulator, Image processing, Machine Learning, TensorFlow,Abstract
The insulator plays an essential role in preventing the flow of current from the phase conductor to the earth through supporting towers so that the insulation is a significant part of the electrical energy transmission system. Generally, high-voltage insulators are widely used as external plug insulators, for that the performance of insulators is influenced by environmental conditions that indirectly affect the surface condition of the insulators. In this study, a diagnostic tool used in the testing surface of the insulator, which can classify mechanically whether the insulator is good or damaged. The classification method uses TensorFlow Machine learning. Machine Learning is used as a brain in the isolation classification process while TensorFlow functions to store training data and test data in the classification process. The results obtained from this study show the accuracy of classification data is 98%.References
M. Nurhuda, Mendulang Energi Gratis dengan Teknologi Tepat Guna: Universitas Brawijaya Press, 2018.
Mustamin and S. Manjang, "Karakteristik Isolator Polimer Tegangan Tinggi di Bawah Penuaan Tekanan Iklim Tropis Buatan yang Di Percepat," SINERGI, Jurnal Teknik Mesin Politeknik Negeri Ujung Pandang, vol. 9, pp. 23-37, 2011.
K. H.C. and S. A, "The Dielectric Properties of Fibre Reinforced Epoxies under the Influence of Humidity," Proceeding of the 4th ICPADM., Brisbane. , 1994.
D. Pernebayeva, M. Bagheri, and A. James, "High voltage insulator surface evaluation using image processing," in 2017 International Symposium on Electrical Insulating Materials (ISEIM), 2017, pp. 520-523.
X. Mei, T. Lu, X. Wu, and B. Zhang, "Insulator surface dirt image detection technology based on improved watershed algorithm," in 2012 Asia-Pacific Power and Energy Engineering Conference, 2012, pp. 1-5.
M. Oberweger, A. Wendel, and H. Bischof, "Visual recognition and fault detection for power line insulators," in 19th computer vision winter workshop, 2014, pp. 1-8.
F. Gao, J. Wang, Z. Kong, J. Wu, N. Feng, S. Wang, et al., "Recognition of insulator explosion based on deep learning," in 2017 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), 2017, pp. 79-82.
M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, et al., "Tensorflow: A system for large-scale machine learning," in 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), 2016, pp. 265-283.
M. Feys., "Introduction to TensorFlow ", https://www.tensorflow.org, GDG Cloud Belgium, 2016
S. Ren, He, K., Girshick, R. and Sun, J., "Faster r-cnn: Towards real-time object detection with region proposal networks. ," Advances in neural information processing systems, pp. (pp. 91-99). 2015
https://www.tensorflow.org, "Image Recognition/ tutorials," 2019.
Sebastian Raschka, "What is Softmax Regression and How is it Related to Logistic Regression," https://www.kdnuggets.com, vol. di akses pada tanggal 26 Januari 2020, 2016.
